Mithun Gowda B 89a5cf33d6
Fixes and improvement (#378)
* Fix: Install only selected MCP servers and ensure valid empty backups

This commit addresses two separate issues:

1.  **MCP Installation:** The `install` command was installing all MCP servers instead of only the ones selected by the user. The `_install` method in `setup/components/mcp.py` was iterating through all available servers, not the user's selection. This has been fixed to respect the `selected_mcp_servers` configuration. A new test has been added to verify this fix.

2.  **Backup Creation:** The `create_backup` method in `setup/core/installer.py` created an invalid `.tar.gz` file when the backup source was empty. This has been fixed to ensure that a valid, empty tar archive is always created. A test was added for this as well.
Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* Fix: Correct installer validation for MCP and MCP Docs components

This commit fixes a validation issue in the installer where it would incorrectly fail after a partial installation of MCP servers.

The `MCPComponent` validation logic was checking for all "required" servers, regardless of whether they were selected by the user. This has been corrected to only validate the servers that were actually installed, by checking against the list of installed servers stored in the metadata. The metadata storage has also been fixed to only record the installed servers.

The `MCPDocsComponent` was failing validation because it was not being registered in the metadata if no documentation files were installed. This has been fixed by ensuring the post-installation hook runs even when no files are copied.

New tests have been added for both components to verify the corrected logic.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* Fix: Allow re-installation of components and correct validation logic

This commit fixes a bug that prevented new MCP servers from being installed on subsequent runs of the installer. It also fixes the validation logic that was causing failures after a partial installation.

The key changes are:
1.  A new `is_reinstallable` method has been added to the base `Component` class. This allows certain components (like the `mcp` component) to be re-run even if they are already marked as installed.
2.  The installer logic has been updated to respect this new method.
3.  The `MCPComponent` now correctly stores only the installed servers in the metadata.
4.  The validation logic for `MCPComponent` and `MCPDocsComponent` has been corrected to prevent incorrect failures.

New tests have been added to verify all aspects of the new logic.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* feat: Display authors in UI header and update author info

This commit implements the user's request to display author names and emails in the UI header of the installer.

The key changes are:
1.  The `__email__` field in `SuperClaude/__init__.py` has been updated to include both authors' emails.
2.  The `display_header` function in `setup/utils/ui.py` has been modified to read the author and email information and display it.
3.  A new test has been added to `tests/test_ui.py` to verify the new UI output.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* feat: Version bump to 4.1.0 and various fixes

This commit prepares the project for the v4.1.0 release. It includes a version bump across all relevant files and incorporates several bug fixes and feature enhancements from recent tasks.

Key changes in this release:

- **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 in all configuration files, documentation, and source code.

- **Installer Fixes**:
  - Components can now be marked as `reinstallable`, allowing them to be re-run on subsequent installations. This fixes a bug where new MCP servers could not be added.
  - The validation logic for `mcp` and `mcp_docs` components has been corrected to avoid incorrect failures.
  - A bug in the backup creation process that created invalid empty archives has been fixed.

- **UI Enhancements**:
  - Author names and emails are now displayed in the installer UI header.

- **Metadata Updates**:
  - Mithun Gowda B has been added as an author.

- **New Tests**:
  - Comprehensive tests have been added for the installer logic, MCP components, and UI changes to ensure correctness and prevent regressions.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* fix: Resolve dependencies for partial installs and other fixes

This commit addresses several issues, the main one being a dependency resolution failure during partial installations.

Key changes:
- **Dependency Resolution**: The installer now correctly resolves the full dependency tree when a user requests to install a subset of components. This fixes the "Unknown component: core" error.
- **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run on subsequent installs, enabling the addition of new servers.
- **Validation Logic**: The validation for `mcp` and `mcp_docs` has been corrected to avoid spurious failures.
- **UI and Metadata**: Author information has been added to the UI header and source files.
- **Version Bump**: The project version has been updated to 4.1.0.
- **Tests**: New tests have been added to cover all the above changes.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* fix: Installer fixes and version bump to 4.1.0

This commit includes a collection of fixes for the installer logic, UI enhancements, and a version bump to 4.1.0.

Key changes:
- **Dependency Resolution**: The installer now correctly resolves the full dependency tree for partial installations, fixing the "Unknown component: core" error.
- **Component Re-installation**: A new `is_reinstallable` flag allows components like `mcp` to be re-run to add new servers.
- **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts the user to select servers.
- **Validation Logic**: The post-installation validation logic has been corrected to only validate components from the current session and to use the correct list of installed servers.
- **UI & Metadata**: Author information has been added to the UI and source files.
- **Version Bump**: The project version has been updated from 4.0.9 to 4.1.0 across all files.
- **Tests**: New tests have been added to cover all the bug fixes.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* feat: Add --authors flag and multiple installer fixes

This commit introduces the `--authors` flag to display author information and includes a collection of fixes for the installer logic.

Key changes:
- **New Feature**: Added an `--authors` flag that displays the names, emails, and GitHub usernames of the project authors.
- **Dependency Resolution**: Fixed a critical bug where partial installations would fail due to unresolved dependencies.
- **Component Re-installation**: Added a mechanism to allow components to be "reinstallable", fixing an issue that prevented adding new MCP servers on subsequent runs.
- **MCP Installation**: The non-interactive installation of the `mcp` component now correctly prompts for server selection.
- **Validation Logic**: Corrected the post-installation validation to prevent spurious errors.
- **Version Bump**: The project version has been updated to 4.1.0.
- **Metadata**: Author and GitHub information has been added to the source files.
- **UI**: The installer header now displays author information.
- **Tests**: Added new tests for all new features and bug fixes.

Co-authored-by: Mithun Gowda B <mithungowda.b7411@gmail.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>

* Add Docker support and framework enhancements

- Add serena-docker.json MCP configuration
- Update MCP configs and installer components
- Enhance CLI commands with new functionality
- Add symbols utility for framework operations
- Improve UI and logging components

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Bump version from 4.1.1 to 4.1.2

- Update version across all package files
- Update documentation and README files
- Update Python module version strings
- Update feature configuration files

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com>

* Bump version from 4.1.2 to 4.1.3

- Update version across all package files
- Update documentation and README files
- Update Python module version strings
- Update feature configuration files

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com>

* Fix home directory detection for immutable distros

- Add get_home_directory() function to handle /var/home/$USER paths
- Support Fedora Silverblue, Universal Blue, and other immutable distros
- Replace all Path.home() calls throughout the setup system
- Add fallback methods for edge cases and compatibility
- Create test script for immutable distro validation

Fixes:
- Incorrect home path detection on immutable Linux distributions
- Installation failures on Fedora Silverblue/Universal Blue
- Issues with Claude Code configuration paths

Technical changes:
- New get_home_directory() in utils/environment.py
- Updated all CLI commands, validators, and core components
- Maintains backward compatibility with standard systems
- Robust fallback chain for edge cases

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com>

* Fix circular import and complete immutable distro support

- Move get_home_directory() to separate paths.py module
- Resolve circular import between environment.py and logger.py
- Update all import statements across the setup system
- Verify functionality with comprehensive testing

Technical changes:
- Created setup/utils/paths.py for path utilities
- Updated imports in all affected modules
- Maintains full backward compatibility
- Fixes installation on immutable distros

Testing completed:
- ✅ Basic home directory detection works
- ✅ Installation system integration works
- ✅ Environment utilities integration works
- ✅ Immutable distro logic validated

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Co-Authored-By: Mithun Gowda B <mithungowda.b7411@gmail.com>

* Fix mcp_docs installation bugs

- Fix mcp_docs component incorrectly marking as installed when no MCP servers selected
- Add MCP server selection prompt when mcp_docs component is explicitly requested
- Return False instead of calling _post_install() when no servers selected or files found
- Add user-friendly warning when mcp_docs requested without server selection
- Remove mcp_docs from installation when no servers are available

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Fix MCP server name mapping for documentation files

- Add mapping for sequential-thinking -> MCP_Sequential.md
- Add mapping for morphllm-fast-apply -> MCP_Morphllm.md
- Ensures mcp_docs installation works with all MCP server naming conventions

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Enable mcp_docs component reinstallation

- Add is_reinstallable() method returning True to allow repeat installations
- Fixes issue where mcp_docs was skipped on subsequent installation attempts
- Enables users to change MCP server selections and update documentation

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Fix repeat installation issues for mcp_docs

- Ensure mcp component is auto-added when mcp_docs is selected with servers
- Fix component_files tracking to only include successfully copied files
- Ensures CLAUDE.md gets properly updated with MCP documentation imports
- Fixes issue where MCP servers weren't installed on repeat attempts

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Fix MCP component metadata tracking and debug logging

- Fix servers_count to track actually installed servers instead of total available
- Add installed_servers list to metadata for better tracking
- Add debug logging to trace component auto-addition
- Ensures MCP component appears properly in metadata when servers are installed

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Fix pyproject.toml license format and add missing classifier

- Fix license format from string to {text = "MIT"} format
- Add missing "License :: OSI Approved :: MIT License" classifier
- Fix indentation consistency in classifiers section
- Resolves setup.py installation errors and PEP 621 compliance

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Fix MCP incremental installation and auto-detection system

PROBLEM FIXED:
- MCP component only registered servers selected during current session
- mcp_docs component only installed docs for newly selected servers
- Users had to reinstall everything when adding new MCP servers
- Installation failed if no servers selected but servers existed

SOLUTION IMPLEMENTED:
- Add auto-detection of existing MCP servers from config files (.claude.json, claude_desktop_config.json)
- Add CLI detection via 'claude mcp list' output parsing
- Add smart server merging (existing + selected + previously installed)
- Add server name normalization for common variations
- Fix CLI logic to allow mcp_docs installation without server selection
- Add graceful error handling for corrupted configs

KEY FEATURES:
✅ Auto-detects existing MCP servers from multiple config locations
✅ Supports incremental installation (add new servers without breaking existing)
✅ Works with or without --install-dir argument
✅ Handles server name variations (sequential vs sequential-thinking, etc.)
✅ Maintains metadata persistence across installation sessions
✅ Graceful fallback when config files are corrupted
✅ Compatible with both interactive and non-interactive modes

TESTED SCENARIOS:
- Fresh installation with no MCP servers ✅
- Auto-detection with existing servers ✅
- Incremental server additions ✅
- Mixed mode (new + existing servers) ✅
- Error handling with corrupted configs ✅
- Default vs custom installation directories ✅
- Interactive vs command-line modes ✅

Files changed:
- setup/cli/commands/install.py: Allow mcp_docs auto-detection mode
- setup/components/mcp.py: Add comprehensive auto-detection logic
- setup/components/mcp_docs.py: Add auto-detection for documentation

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Integrate SuperClaude framework flags into help command

ENHANCEMENT:
- Add comprehensive flag documentation to /sc:help command
- Include all 25 SuperClaude framework flags with descriptions
- Organize flags into logical categories (Mode, MCP, Analysis, Execution, Output)
- Add practical usage examples showing flag combinations
- Include flag priority rules and precedence hierarchy

NEW SECTIONS ADDED:
✅ Mode Activation Flags (5 flags): --brainstorm, --introspect, --task-manage, --orchestrate, --token-efficient
✅ MCP Server Flags (8 flags): --c7, --seq, --magic, --morph, --serena, --play, --all-mcp, --no-mcp
✅ Analysis Depth Flags (3 flags): --think, --think-hard, --ultrathink
✅ Execution Control Flags (6 flags): --delegate, --concurrency, --loop, --iterations, --validate, --safe-mode
✅ Output Optimization Flags (3 flags): --uc, --scope, --focus
✅ Flag Priority Rules: Clear hierarchy and precedence guidelines
✅ Usage Examples: 4 practical examples showing real-world flag combinations

IMPACT:
- Users can now discover all SuperClaude capabilities from /sc:help
- Single source of truth for commands AND flags
- Improved discoverability of advanced features
- Clear guidance on flag usage and combinations
- Help content nearly doubled (68 → 148 lines) with valuable reference information

Files changed:
- SuperClaude/Commands/help.md: Integrate FLAGS.md content with structured tables and examples

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Remove non-existent commands from modes.md documentation

PROBLEM FIXED:
- Documentation contained references to fake/non-existent commands
- Commands like sc:fix, sc:simple-pix, sc:update, sc:develop, sc:modernize, sc:simple-fix don't exist in CLI
- Confusing users who try to use these commands and get errors
- Inconsistency between documentation and actual SuperClaude command availability

COMMANDS REMOVED/REPLACED:
❌ /sc:simple-fix → ✅ /sc:troubleshoot (real command)
❌ /sc:develop → ✅ /sc:implement (real command)
❌ /sc:modernize → ✅ /sc:improve (real command)

AFFECTED FILES:
- Docs/User-Guide/modes.md: Fixed all non-existent command references
- Docs/User-Guide-jp/modes.md: Fixed Japanese translation with same issues
- Docs/User-Guide-zh/modes.md: Fixed Chinese translation with same issues

VERIFICATION:
✅ All remaining /sc: commands verified to exist in SuperClaude/Commands/
✅ No more references to fake commands in any language version
✅ Examples now use only real, working SuperClaude commands
✅ User experience improved - no more confusion from non-working commands

REAL COMMANDS REFERENCED:
- /sc:analyze, /sc:brainstorm, /sc:help, /sc:implement
- /sc:improve, /sc:reflect, /sc:troubleshoot
- All verified to exist in CLI implementation

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* Version bump to 4.1.4

CHANGELOG:
✅ Added comprehensive flag documentation to /sc:help command
✅ Fixed MCP incremental installation and auto-detection system
✅ Cleaned up documentation by removing non-existent commands
✅ Enhanced user experience with complete capability reference

VERSION UPDATES:
- Updated VERSION file: 4.1.3 → 4.1.4
- Updated pyproject.toml: 4.1.3 → 4.1.4
- Updated package.json: 4.1.3 → 4.1.4
- Updated all Python __init__.py fallback versions
- Updated all documentation references across all languages
- Updated setup/data/features.json component versions
- Updated CHANGELOG.md with comprehensive 4.1.4 release notes

SCOPE OF CHANGES:
📊 Core files: VERSION, pyproject.toml, package.json, __init__.py files
📚 Documentation: All .md files across English, Japanese, Chinese
🔧 Setup files: features.json, base.py version references
📝 Project files: README files, CHANGELOG, SECURITY, CONTRIBUTING

VERIFICATION:
✅ No remaining 4.1.3 references found
✅ 29 files now properly reference 4.1.4
✅ All language versions consistently updated
✅ Package metadata properly versioned for distribution

🀖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

---------

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: Jules <jules-ai-assistant@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
2025-09-20 14:08:42 +05:30

36 KiB
Raw Blame History

SuperClaude 行動モヌドガむド 🧠

✅ クむック怜蚌

コマンドを䜿甚しおモヌドをテストしたす/sc:。モヌドはタスクの耇雑さに基づいお自動的にアクティブになりたす。コマンドの完党なリファレンスに぀いおは、コマンドガむドをご芧ください。

クむックリファレンステヌブル

モヌド 目的 自動トリガヌ 重芁な行動 最適な甚途
🧠 ブレむンストヌミング むンタラクティブな発芋 「ブレむンストヌミング」、「たぶん」、挠然ずした芁望 ゜クラテス匏の質問、芁件の抜出 新しいプロゞェクトの蚈画、䞍明確な芁件
🔍 内省 メタ認知分析 ゚ラヌ回埩、「掚論の分析」 透明な思考マヌカヌ🀔、🎯、💡 デバッグ、孊習、最適化
📋 タスク管理 耇雑な調敎 >3ステップ、>2ディレクトリ 盞の厩壊、蚘憶の持続 倚段階操䜜、プロゞェクト管理
🎯 オヌケストレヌション むンテリゞェントなツヌル遞択 耇数のツヌルを䜿甚した操䜜、高いリ゜ヌス䜿甚率 最適なツヌルルヌティング、䞊列実行 耇雑な分析、パフォヌマンスの最適化
⚡ トヌクン効率 圧瞮通信 コンテキスト䜿甚率が高い、--ucフラグ シンボルシステム、掚定3050%のトヌクン削枛 リ゜ヌスの制玄、倧芏暡な操䜜

はじめに2分の抂芁

モヌドは動䜜指瀺を通じおアクティブ化されたす- Claude Code はコンテキスト ファむルを読み取り、タスクのパタヌンず耇雑さに基づいおどのモヌド動䜜を採甚するかを決定したす。

簡単な䟋:

# Automatic activation examples
/sc:brainstorm "mobile app"        # → Socratic discovery questions
/sc:implement "auth system"        # → Multi-phase coordination  
"--uc analyze large-codebase/"     # → Compressed symbol output

手動フラグを䜿甚する堎合:

  • 特定の動䜜が必芁: --brainstorm、、--introspect``--uc
  • å­Šç¿’/デバッグのための自動怜出をオヌバヌラむドする
  • 特定の制玄メモリ、時間、明瞭性に合わせお最適化する

モヌドの詳现

🧠 ブレむンストヌミングモヌド - むンタラクティブな発芋

目的: 共同䜜業による発芋を通じお、挠然ずしたアむデアを構造化された芁件に倉換したす。

自動アクティベヌショントリガヌ:

  • 挠然ずしたプロゞェクトリク゚スト:「...を構築したい」、「...を䜜成しようず考えおいる」
  • 探玢キヌワヌド: ブレむンストヌミング、探玢、議論、理解、䞍明
  • 䞍確実性指暙「たぶん」、「おそらく」、「できるかもしれない」
  • 手動フラグ: --brainstorm、--bs

行動の倉化:

  • ゜クラテス匏質問隠れた芁件を明らかにするために掘り䞋げた質問をする
  • 非掚定的アプロヌチ掚定を避け、発芋の方向性を導く
  • 協力的なパヌトナヌシップ指瀺的な盞談ではなく、探玢的に協力したす
  • 芁件統合掞察を構造化された技術抂芁に倉換したす
  • クロスセッションメモリフォロヌアップの議論のために発芋のコンテキストを維持する

経隓䟋:

Standard Approach: "I'll build a user authentication system with JWT tokens..."
Brainstorming Approach: 
"🀔 Let's explore this together:
 - What specific user problems does auth solve for your app?
 - Who are your users and what's their technical comfort level?  
 - Any existing systems or social logins to integrate with?
 - What security/compliance requirements do you have?
 📝 Outcome: Detailed auth requirements brief ready for implementation"

成功基準

  • すぐに解決策を提瀺するのではなく、質問で応答する
  • 質問はナヌザヌのニヌズ、技術的制玄、ビゞネス目暙を探りたす
  • 発芋プロセス党䜓を通じお協力的な姿勢を維持する
  • 結果ずしお構造化された芁件たたは技術抂芁を䜜成したす

怜蚌: /sc:brainstorm "web app"ナヌザヌ、機胜、テクノロゞヌに぀いお質問する必芁がありたす。
**テスト:**挠然ずしたリク゚ストは、掚枬ではなく発芋のための質問を匕き起こす必芁がありたす。
**チェック:**モヌドは、同じ䌚話内のフォロヌアップの質問でも維持される必芁がありたす。

最適な組み合わせ:

  • → タスク管理芁件の発芋 → 䜓系的な実装蚈画
  • → オヌケストレヌション芁件の明確化 → 実装に最適なツヌルの遞択
  • 手動オヌバヌラむド: --brainstorm「明確な」芁件であっおも匷制的に怜出するために䜿甚したす

🔍 内省モヌド - メタ認知分析

目的: 孊習の最適化ず透明な意思決定のための掚論プロセスを公開したす。

自動アクティベヌショントリガヌ:

  • 自己分析の芁求「自分の掚論を分析する」、「決定を振り返る」
  • ゚ラヌ回埩シナリオず調査を必芁ずする予期しない結果
  • 耇数の実行可胜なアプロヌチによる耇雑な問題解決
  • 最適化の機䌚のためのパタヌン認識の必芁性
  • 手動フラグ:--introspect

行動の倉化:

  • 掚論の透明性: 思考プロセスを明確なマヌカヌで公開したす (🀔、🎯、⚡、📊、💡)
  • 意思決定分析遞択ロゞックを評䟡し、代替アプロヌチを怜蚎する
  • パタヌン認識繰り返される行動ず改善の機䌚を特定したす
  • メタ孊習継続的なフレヌムワヌク改善のための掞察を抜出
  • フレヌムワヌクコンプラむアンス: SuperClaude原則ず品質ゲヌトに照らしおアクションを怜蚌したす

経隓䟋:

Standard Approach: "I'll analyze this code structure and suggest improvements..."
Introspective Approach:
"🧠 Meta-Analysis: Why did I choose structural analysis over functional flow?
 🎯 Decision Logic: Saw class hierarchy → assumed OOP pattern dominance
 🔄 Alternative Considered: Data flow analysis might reveal hidden dependencies
 📊 Evidence Check: File imports suggest functional composition, not OOP
 💡 Learning: Need to analyze imports before choosing analysis strategy
 ⚡ Correction: Switching to functional flow analysis approach"

最適な組み合わせ:

  • → タスク管理: 耇雑なフェヌズの決定に透明な掚論を提䟛したす
  • 任意のモヌド: 他のモヌドの操䜜に掚論の透明性レむダヌを远加したす
  • 手動オヌバヌラむド:--introspect孊習セッションやワヌクフロヌのデバッグに䜿甚したす

📋 タスク管理モヌド - 耇雑な調敎

目的: 耇数ステップの操䜜のためのセッション氞続性を備えた階局的なタスク構成。

自動アクティベヌショントリガヌ:

  • 3 ぀以䞊の調敎されたステップを必芁ずする操䜜
  • 耇数のファむル/ディレクトリ スコヌプ (ディレクトリが 2 ぀以䞊、たたはファむル数が 3 ぀以䞊)
  • フェヌズずチェックポむントを必芁ずする耇雑な䟝存関係
  • 品質改善の芁望磚き、掗緎、匷化
  • 手動フラグ: --task-manage、--delegate

行動の倉化:

  • 階局的蚈画耇雑な䜜業を蚈画→フェヌズ→タスク→ToDo構造に分割したす
  • セッションの氞続性: 䞭断があっおもプロゞェクトのコンテキストず進行状況を維持したす
  • メモリ統合: 状態保存のために write_memory/read_memory を䜿甚する
  • 進捗オヌケストレヌション: 远跡のためにメモリ曎新ずTodoWriteを調敎する
  • 品質ゲヌト:フェヌズ間の䜓系的な怜蚌チェックポむントを実装したす

経隓䟋:

Standard Approach: "I'll implement user authentication..." → Direct implementation
Task Management Approach:
"📋 Multi-Phase Implementation Plan:
 🎯 Phase 1: Security Requirements Analysis (Session 1)
 🎯 Phase 2: API Design & Documentation (Session 2)  
 🎯 Phase 3: Implementation & Testing (Session 3-4)
 🎯 Phase 4: Integration & Validation (Session 5)
 💟 Session persistence: Resume context automatically
 ✓ Quality gates: Validation before each phase transition"

最適な組み合わせ:

  • ブレむンストヌミング→芁件発芋ず䜓系的な実装
  • + オヌケストレヌション: 最適なツヌル遞択によるタスク調敎
  • + むントロスペクション耇雑なフェヌズの決定のための透過的な掚論

🎯 オヌケストレヌションモヌド - むンテリゞェントなツヌル遞択

目的: むンテリゞェントなツヌルルヌティングず䞊列調敎を通じおタスクの実行を最適化したす。

自動アクティベヌショントリガヌ:

  • 高床な調敎を必芁ずするマルチツヌル操䜜
  • パフォヌマンス制玄リ゜ヌス䜿甚量が倚い
  • 䞊列実行の機䌚3぀以䞊の独立したファむル/操䜜
  • 耇数の有効なツヌルアプロヌチによる耇雑なルヌティング決定

行動の倉化:

  • むンテリゞェントツヌルルヌティング:各タスクタむプに最適なMCPサヌバヌずネむティブツヌルを遞択したす。
  • リ゜ヌス認識: システムの制玄ず可甚性に基づいおアプロヌチを適応させたす
  • 䞊列最適化: 同時実行のための独立した操䜜を識別したす
  • 調敎の焊点調敎された実行を通じおツヌルの遞択ず䜿甚を最適化したす
  • アダプティブフォヌルバック: 優先オプションが利甚できない堎合にツヌルを適切に切り替えたす

経隓䟋:

Standard Approach: Sequential file-by-file analysis and editing
Orchestration Approach:
"🎯 Multi-Tool Coordination Strategy:
 🔍 Phase 1: Serena (semantic analysis) + Sequential (architecture review)
 ⚡ Phase 2: Morphllm (pattern edits) + Magic (UI components) 
 🧪 Phase 3: Playwright (testing) + Context7 (documentation patterns)
 🔄 Parallel execution: 3 tools working simultaneously
\"

最適な組み合わせ:

  • タスク管理 → : 耇雑な倚段階蚈画のためのツヌル調敎を提䟛したす
  • + トヌクン効率: 圧瞮通信による最適なツヌル遞択
  • 耇雑なタスク: むンテリゞェントなツヌルルヌティングを远加しお実行を匷化

⚡ トヌクン効率モヌド - 圧瞮通信

目的: 情報の品質を維持しながら、シンボル システムを通じお掚定 30  50% のトヌクン削枛を実珟したす。

自動アクティベヌショントリガヌ:

  • 高いコンテキストの䜿甚が限界に近づいおいたす
  • 資源効率が求められる倧芏暡運甚
  • ナヌザヌ明瀺フラグ: --uc、--ultracompressed
  • 耇数の出力を持぀耇雑な分析ワヌクフロヌ

行動の倉化:

  • シンボルコミュニケヌション: ロゞックフロヌ、ステヌタス、技術ドメむンに芖芚的なシンボルを䜿甚したす
  • 技術略語繰り返される技術甚語のコンテキスト認識圧瞮
  • 構造化された密床: 冗長な段萜よりも箇条曞き、衚、簡朔な曞匏
  • 情報保存: 圧瞮しおも95%以䞊の情報品質を維持
  • 構造化されたフォヌマット: 明確さずタスクの完了のために敎理されおいたす

経隓䟋:

Standard Approach: "The authentication system implementation shows a security vulnerability in the user validation function that needs immediate attention..."
Token Efficient Approach:
"🛡 Security Alert:
 auth.js:45 → user val() → critical vuln
 📊 Impact: ❌ token bypass possible
 ⚡ Action: fix validation + audit ∵ high sev
 🔧 Est: 2h impl + 1h test"

最適な組み合わせ:

  • 任意のモヌド: モヌド固有の動䜜を維持しながら圧瞮レむダヌを远加したす
  • オヌケストレヌション → : 圧瞮されたツヌル調敎ずステヌタス曎新
  • 手動オヌバヌラむド:--ucコンテキストのプレッシャヌや効率が優先される堎合に䜿甚したす

🎚 暙準モヌド - バランスのずれたデフォルト

目的: 簡単な開発タスクに察しお明確でプロフェッショナルなコミュニケヌションを提䟛したす。

自動アクティベヌショントリガヌ:

  • 耇雑さの指暙のない、シンプルで明確に定矩されたタスク
  • 明確な芁件を備えた単䞀ファむル操䜜
  • 基本的な説明ず暙準的な開発ワヌクフロヌ
  • 他のモヌドトリガヌは怜出されたせんデフォルトのフォヌルバック

行動の倉化:

  • プロフェッショナルなコミュニケヌション明確で簡朔な技術甚語
  • 䞭皋床の詳现: ほずんどの開発タスクに適したバランスの取れた情報の深さ
  • 暙準ツヌル遞択: ネむティブのClaude機胜ず基本ツヌルを䜿甚
  • 品質重芖: 耇雑なオヌケストレヌションのオヌバヌヘッドなしでコヌドの品質を維持
  • 応答的な適応耇雑さが増すず、特化したモヌドに切り替える準備ができおいたす

経隓䟋:

Standard Approach: Consistent, professional baseline for all tasks
"I'll implement the login function with proper error handling:
 
 1. Validate user input (email format, password requirements)
 2. Authenticate against database with secure hashing
 3. Generate JWT token with appropriate expiration
 4. Return success response with user data
 
 The implementation will follow security best practices and include comprehensive error handling."

最適な組み合わせ:

  • → 任意のモヌド: 他のモヌドを匷化する基準ずしお機胜したす
  • モヌド切り替え: 必芁に応じお自動的に特殊モヌドに切り替えたす
  • 明確さの優先: 最適化よりも分かりやすいコミュニケヌションが重芁な堎合

高床な䜿甚法

モヌドの組み合わせ

マルチモヌドワヌクフロヌ:

# Discovery → Planning → Implementation
/sc:brainstorm "microservices architecture" --task-manage
# → Brainstorming: requirement discovery
# → Task Management: multi-phase coordination

# Analysis with transparency and efficiency
/sc:analyze legacy-system/ --introspect --uc
# → Introspection: transparent reasoning
# → Token Efficiency: compressed output

手動モヌド制埡

特定の動䜜を匷制する:

  • --brainstorm: あらゆるタスクで共同発芋を匷制
  • --introspect: あらゆるモヌドに掚論の透明性を远加
  • --task-manage: 階局的な調敎を可胜にする
  • --orchestrate: ツヌル遞択ず䞊列実行を最適化
  • --uc: 効率化のために通信を圧瞮する

オヌバヌラむドの䟋:

# Force brainstorming on "clear" requirements
/sc:implement "user login" --brainstorm

# Add reasoning transparency to debugging
# 認蚌問題を透明な掚理でデバッグ

# Enable task management for simple operations
# システマチックなタスク管理でスタむルファむルを曎新

モヌドの境界ず優先順䜍

モヌドがアクティブになるず:

  1. 耇雑さの閟倀: >3ファむル → タスク管理
  2. リ゜ヌスの圧力コンテキスト䜿甚率が高い → トヌクン効率
  3. 耇数のツヌルが必芁: 耇雑な分析 → オヌケストレヌション
  4. 䞍確実性挠然ずした芁件 → ブレむンストヌミング
  5. ゚ラヌ回埩問題 → むントロスペクション

優先ルヌル:

  • 安党第䞀品質ず怜蚌は垞に効率よりも優先されたす
  • ナヌザヌの意図: 手動フラグは自動怜出を䞊曞きしたす
  • コンテキスト適応: 耇雑さに基づいおモヌドをスタック
  • リ゜ヌス管理プレッシャヌ䞋では効率モヌドが掻性化する

実䞖界の䟋

完党なワヌクフロヌの䟋

新芏プロゞェクト開発:

# Phase 1: Discovery (Brainstorming Mode auto-activates)
"I want to build a productivity app"
→ 🀔 Socratic questions about users, features, platform choice
→ 📝 Structured requirements brief

# Phase 2: Planning (Task Management Mode auto-activates)  
/sc:implement "core productivity features"
→ 📋 Multi-phase breakdown with dependencies
→ 🎯 Phase coordination with quality gates

# Phase 3: Implementation (Orchestration Mode coordinates tools)
/sc:implement "frontend and backend systems"
→ 🎯 Magic (UI) + Context7 (patterns) + Sequential (architecture)
→ ⚡ Parallel execution optimization

耇雑な問題のデバッグ:

# Problem analysis (Introspection Mode auto-activates)
"Users getting intermittent auth failures"
→ 🀔 Transparent reasoning about potential causes
→ 🎯 Hypothesis formation and evidence gathering
→ 💡 Pattern recognition across similar issues

# Systematic resolution (Task Management coordinates)
# 認蚌システムを包括的に修正
→ 📋 Phase 1: Root cause analysis
→ 📋 Phase 2: Solution implementation  
→ 📋 Phase 3: Testing and validation

モヌドの組み合わせパタヌン

非垞に耇雑なシナリオ:

# Large refactoring with multiple constraints
/sc:improve legacy-system/ --introspect --uc --orchestrate
→ 🔍 Transparent reasoning (Introspection)
→ ⚡ Compressed communication (Token Efficiency)  
→ 🎯 Optimal tool coordination (Orchestration)
→ 📋 Systematic phases (Task Management auto-activates)

クむックリファレンス

モヌド起動パタヌン

トリガヌタむプ 入力䟋 モヌドが有効 䞻芁な動䜜
挠然ずした芁求 「アプリを䜜りたい」 🧠 ブレむンストヌミング ゜クラテス匏の発芋的質問
耇雑なスコヌプ >3 ぀のファむルたたは >2 ぀のディレクトリ 📋 タスク管理 䜍盞調敎
マルチツヌルの必芁性 分析 + 実装 🎯 オヌケストレヌション ツヌルの最適化
゚ラヌ回埩 「期埅通りに動䜜しおいたせん」 🔍 内省 透明な掚論
リ゜ヌスの圧力 高コンテキスト䜿甚 ⚡ トヌクン効率 シンボル圧瞮
簡単なタスク 「この機胜を修正する」 🎚 暙準 明確で盎接的なアプロヌチ

手動オヌバヌラむドコマンド

# Force specific mode behaviors
/sc:command --brainstorm    # Collaborative discovery
/sc:command --introspect    # Reasoning transparency
/sc:command --task-manage   # Hierarchical coordination
/sc:command --orchestrate   # Tool optimization
/sc:command --uc           # Token compression

# Combine multiple modes
/sc:command --introspect --uc    # Transparent + efficient
/sc:command --task-manage --orchestrate  # Coordinated + optimized

トラブルシュヌティング

トラブルシュヌティングのヘルプに぀いおは、以䞋を参照しおください。

よくある問題

  • モヌドがアクティブ化されおいたせん: 手動フラグを䜿甚しおください: --brainstorm、、--introspect``--uc
  • 間違ったモヌドがアクティブです: リク゚スト内の耇雑なトリガヌずキヌワヌドを確認しおください
  • 予期しないモヌド切り替えタスクの進行に基づく通垞の動䜜
  • 実行ぞの圱響: モヌドはツヌルの䜿甚を最適化するものであり、実行には圱響しないはずです。
  • モヌドの競合:フラグガむドでフラグの優先順䜍ルヌルを確認しおください

即時修正

  • 特定のモヌドを匷制:--brainstormたたはのような明瀺的なフラグを䜿甚する--task-manage
  • リセットモヌドの動䜜: モヌド状態をリセットするには、Claude Code セッションを再起動したす。
  • モヌドむンゞケヌタヌを確認する: 応答に🀔、🎯、📋の蚘号があるかどうかを確認したす
  • 耇雑さを怜蚌: 単玔なタスクは暙準モヌドを䜿甚し、耇雑なタスクは自動的に切り替わりたす

モヌド固有のトラブルシュヌティング

ブレむンストヌミングモヌドの問題:

# Problem: Mode gives solutions instead of asking questions
# Quick Fix: Check request clarity and use explicit flag
/sc:brainstorm "web app" --brainstorm         # Force discovery mode
"I have a vague idea about..."                # Use uncertainty language
"Maybe we could build..."                     # Trigger exploration

タスク管理モヌドの問題:

# Problem: Simple tasks getting complex coordination
# Quick Fix: Reduce scope or use simpler commands
/sc:implement "function" --no-task-manage     # Disable coordination
/sc:troubleshoot bug.js                       # Use basic commands
# Check if task really is complex (>3 files, >2 directories)

トヌクン効率モヌドの問題:

# Problem: Output too compressed or unclear
# Quick Fix: Disable compression for clarity
/sc:command --no-uc                           # Disable compression
/sc:command --verbose                         # Force detailed output
# Use when clarity is more important than efficiency

むントロスペクションモヌドの問題:

# Problem: Too much meta-commentary, not enough action
# Quick Fix: Disable introspection for direct work
/sc:command --no-introspect                   # Direct execution
# Use introspection only for learning and debugging

オヌケストレヌション モヌドの問題:

# Problem: Tool coordination causing confusion
# Quick Fix: Simplify tool usage
/sc:command --no-mcp                          # Native tools only
/sc:command --simple                          # Basic execution
# Check if task complexity justifies orchestration

゚ラヌコヌドリファレンス

モヌド゚ラヌ 意味 クむックフィックス
B001 ブレむンストヌミングが起動できたせんでした --brainstorm明瀺的なフラグを䜿甚する
T001 タスク管理のオヌバヌヘッド --no-task-manage簡単なタスクに䜿甚する
U001 トヌクン効率が匷すぎる 䜿甚--verboseたたは--no-uc
I001 むントロスペクションモヌドが停止したした --no-introspect盎接行動に䜿う
O001 オヌケストレヌション調敎に倱敗 䜿甚--no-mcpたたは--simple
M001 モヌドの競合が怜出されたした フラグの優先順䜍のルヌルを確認する
M002 モヌド切り替えルヌプ 状態をリセットするにはセッションを再起動しおください
M003 モヌドが認識されたせん SuperClaudeを曎新するかスペルをチェックする

プログレッシブサポヌトレベル

レベル 1: クむックフィックス (< 2 分)

  • 自動モヌド遞択を無効にするには手動フラグを䜿甚したす
  • タスクの耇雑さが期埅されるモヌドの動䜜ず䞀臎しおいるかどうかを確認する
  • Claude Codeセッションを再起動しおみおください

レベル2: 詳现なヘルプ515分

# Mode-specific diagnostics
/sc:help modes                            # List all available modes
/sc:reflect --type mode-status            # Check current mode state
# Review request complexity and triggers

レベル3: 専門家によるサポヌト30分以䞊

# Deep mode analysis
SuperClaude install --diagnose
# Check mode activation patterns
# Review behavioral triggers and thresholds

レベル4: コミュニティサポヌト

  • GitHub Issuesでのモヌドの問題の報告
  • 予期しないモヌド動䜜の䟋を含める
  • 望たしいモヌドず実際のモヌドのアクティベヌションを説明する

成功の怜蚌

モヌド修正を適甚した埌、次のようにテストしたす。

  • シンプルなリク゚ストには暙準モヌド明確で盎接的な応答を䜿甚したす
  • 耇雑な芁求は適切なモヌド調敎、掚論を自動的にアクティブ化したす
  • 手動フラグは自動怜出を正しく䞊曞きしたす
  • モヌドむンゞケヌタヌ🀔、🎯、📋は予想通りに衚瀺されたす
  • さたざたなモヌドでパフォヌマンスは良奜です

クむックトラブルシュヌティングレガシヌ

  • モヌドがアクティブ化されない→手動フラグを䜿甚: --brainstorm、、--introspect``--uc
  • 間違ったモヌドがアクティブです→ リク゚スト内の耇雑なトリガヌずキヌワヌドを確認しおください
  • 予期せぬモヌド切り替え→ タスクの進行に基づく通垞の動䜜
  • 実行ぞの圱響→ モヌドはツヌルの䜿甚を最適化するものであり、実行には圱響しないはずです
  • モヌドの競合→フラグガむドでフラグの優先順䜍ルヌルを確認しおください

よくある質問

Q: どのモヌドがアクティブになっおいるかはどうすればわかりたすか? A: 通信パタヌンで次のむンゞケヌタヌを確認しおください。

  • 🀔発芋の質問 → ブレむンストヌミング
  • 🎯 掚論の透明性 → 内省
  • フェヌズの内蚳 → タスク管理
  • ツヌル調敎 → オヌケストレヌション
  • シンボル圧瞮 → トヌクン効率

Q: 特定のモヌドを匷制できたすか? A: はい、手動フラグを䜿甚しお自動怜出をオヌバヌラむドしたす。

/sc:command --brainstorm     # Force discovery
/sc:command --introspect     # Add transparency
/sc:command --task-manage    # Enable coordination
/sc:command --uc            # Compress output

Q: モヌドは実行に圱響したすか? A: モヌドは調敎を通じおツヌルの䜿甚を最適化したす。

  • トヌクン効率: 3050%のコンテキスト削枛
  • オヌケストレヌション䞊列凊理
  • タスク管理䜓系的な蚈画を通じお手戻りを防止

Q: モヌドは連携しお動䜜したすか? A: はい、モヌドは互いに補完し合うように蚭蚈されおいたす。

  • タスク管理は他のモヌドを調敎したす
  • トヌクン効率はあらゆるモヌドの出力を圧瞮する
  • むントロスペクションはあらゆるワヌクフロヌに透明性をもたらしたす

たずめ

SuperClaude の 5 ぀の行動モヌドは、ナヌザヌのニヌズに自動的に適合するむンテリゞェントな適応システムを䜜成したす。

  • 🧠 ブレむンストヌミング挠然ずしたアむデアを明確な芁件に倉換する
  • 🔍 むントロスペクション孊習ずデバッグのための透過的な掚論を提䟛したす
  • 📋 タスク管理耇雑な耇数ステップの操䜜を調敎したす
  • 🎯 オヌケストレヌション: ツヌルの遞択ず䞊列実行を最適化したす
  • ⚡ トヌクン効率: 明瞭さを保ちながらコミュニケヌションを圧瞮する
  • 🎚 暙準: 単玔なタスクに察しおプロフェッショナルな基準を維持したす

重芁な掞察モヌドに぀いお考える必芁はありたせん。モヌドは透過的に動䜜し、開発゚クスペリ゚ンスを向䞊させたす。達成したいこずを説明するだけで、SuperClaudeはニヌズに合わせおアプロヌチを自動的に調敎したす。


関連ガむド

孊習の進捗:

🌱 ゚ッセンシャル第1週

🌿䞭玚第23週

🌲 䞊玚2ヶ月目以降

🔧 ゚キスパヌト

モヌド固有のガむド: